Hey, I'm Raph

From-scratch C++/CUDA inference engine for the NVIDIA RTX 5090 (sm_120a) — the best single-GPU backend for agentic AI: tool calling, long-context loops, reasoning and concurrent sub-agents on top of the fastest single-stream decode on the 5090 (beats llama.cpp, at-or-ahead of vLLM on NVFP4). 100% written by Claude Code.

Recover the CUDA launch and implicit-destructor edges a syntactic indexer loses, written straight into CodeGraph's SQLite graph. On imp (kekzl/imp, 240k lines of C++/CUDA): kernel launch coverage 74.2% → 99.3%, destructors 0% → 85%. On llm.c, which hides nothing, it adds 0 edges.

Local-first AI prompt generator with a Gradio UI: 132 tuned roles for video, image, audio, 3D and creative AI tools. Runs uncensored Dolphin LLMs fully offline, auto-scaled to your GPU VRAM. No API keys, no cloud.

Eine Honigbiene fliegt im Gegenlicht durch eine Sommerwiese — Echtzeit, WebGL2, ohne Build-Schritt

Monitor Entra ID (Azure AD) application secrets and certificates for expiration. Sends alerts via Email, Teams, Slack, or Webhook before credentials expire.

A living, continually learning neuromorphic being — a spiking neural network in C++23/CUDA with purely local plasticity (STDP, R-STDP, and Feedback Alignment instead of backprop). Runs on RTX 5090.

AI-powered email sorting for MailCow - Generate smart Sieve filters automatically using Claude API or local LLMs

Analyze meeting room usage via Microsoft Graph API with a React + FastAPI dashboard